INDEX

Explanations

abbreviations and codes related to scientific experiments

oai_token-act-pair · gemini-2.0-flash

WT

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.50

LayoutStyle

-0.44

QC

-0.41

гин

-0.40

 foly

-0.40

-0.39

-0.38

-0.37

',

-0.37

POSITIVE LOGITS

Хьажоргаш

1.00

Hentet

0.96

PreferredItem

0.91

 uſed

0.90

djangoproject

0.89

 pleaſure

0.88

RectangleBorder

0.85

UnknownFieldSet

0.85

 cherchés

0.84

 myſelf

0.84

Activations Density 6.085%

abbreviations and codes related to scientific experiments

WT

No Comments

No Known Activations